/*
 *  AArch64 translation
 *
 *  Copyright (c) 2013 Alexander Graf <agraf@suse.de>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */
#include "qemu/osdep.h"

#include "cpu.h"
#include "exec/exec-all.h"
#include "tcg-op.h"
#include "qemu/log.h"
#include "arm_ldst.h"
#include "translate.h"
#include "internals.h"
#include "qemu/host-utils.h"

#include "exec/semihost.h"
#include "exec/gen-icount.h"

#include "exec/helper-proto.h"
#include "exec/helper-gen.h"
#include "exec/log.h"

#include "trace-tcg.h"

static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;

/* Load/store exclusive handling */
static TCGv_i64 cpu_exclusive_high;
static TCGv_i64 cpu_reg(DisasContext *s, int reg);

static const char *regnames[] = {
    "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7",
    "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15",
    "x16", "x17", "x18", "x19", "x20", "x21", "x22", "x23",
    "x24", "x25", "x26", "x27", "x28", "x29", "lr", "sp"
};

enum a64_shift_type {
    A64_SHIFT_TYPE_LSL = 0,
    A64_SHIFT_TYPE_LSR = 1,
    A64_SHIFT_TYPE_ASR = 2,
    A64_SHIFT_TYPE_ROR = 3
};

/* Table based decoder typedefs - used when the relevant bits for decode
 * are too awkwardly scattered across the instruction (eg SIMD).
 */
typedef void AArch64DecodeFn(DisasContext *s, uint32_t insn);

typedef struct AArch64DecodeTable {
    uint32_t pattern;
    uint32_t mask;
    AArch64DecodeFn *disas_fn;
} AArch64DecodeTable;

/* Function prototype for gen_ functions for calling Neon helpers */
typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32);
typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64);
typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64);
typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64);
typedef void CryptoTwoOpEnvFn(TCGv_ptr, TCGv_i32, TCGv_i32);
typedef void CryptoThreeOpEnvFn(TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32);

/* initialize TCG globals.  */
void a64_translate_init(void)
{
    int i;

    cpu_pc = tcg_global_mem_new_i64(cpu_env,
                                    offsetof(CPUARMState, pc),
                                    "pc");
    for (i = 0; i < 32; i++) {
        cpu_X[i] = tcg_global_mem_new_i64(cpu_env,
                                          offsetof(CPUARMState, xregs[i]),
                                          regnames[i]);
    }

    cpu_exclusive_high = tcg_global_mem_new_i64(cpu_env,
        offsetof(CPUARMState, exclusive_high), "exclusive_high");
}

static inline ARMMMUIdx get_a64_user_mem_index(DisasContext *s)
{
    /* Return the mmu_idx to use for A64 "unprivileged load/store" insns:
     *  if EL1, access as if EL0; otherwise access at current EL
     */
    switch (s->mmu_idx) {
    case ARMMMUIdx_S12NSE1:
        return ARMMMUIdx_S12NSE0;
    case ARMMMUIdx_S1SE1:
        return ARMMMUIdx_S1SE0;
    case ARMMMUIdx_S2NS:
        g_assert_not_reached();
    default:
        return s->mmu_idx;
    }
}

void aarch64_cpu_dump_state(CPUState *cs, FILE *f,
                            fprintf_function cpu_fprintf, int flags)
{
    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;
    uint32_t psr = pstate_read(env);
    int i;
    int el = arm_current_el(env);
    const char *ns_status;

    cpu_fprintf(f, "PC=%016"PRIx64"  SP=%016"PRIx64"\n",
            env->pc, env->xregs[31]);
    for (i = 0; i < 31; i++) {
        cpu_fprintf(f, "X%02d=%016"PRIx64, i, env->xregs[i]);
        if ((i % 4) == 3) {
            cpu_fprintf(f, "\n");
        } else {
            cpu_fprintf(f, " ");
        }
    }

    if (arm_feature(env, ARM_FEATURE_EL3) && el != 3) {
        ns_status = env->cp15.scr_el3 & SCR_NS ? "NS " : "S ";
    } else {
        ns_status = "";
    }

    cpu_fprintf(f, "\nPSTATE=%08x %c%c%c%c %sEL%d%c\n",
                psr,
                psr & PSTATE_N ? 'N' : '-',
                psr & PSTATE_Z ? 'Z' : '-',
                psr & PSTATE_C ? 'C' : '-',
                psr & PSTATE_V ? 'V' : '-',
                ns_status,
                el,
                psr & PSTATE_SP ? 'h' : 't');

    if (flags & CPU_DUMP_FPU) {
        int numvfpregs = 32;
        for (i = 0; i < numvfpregs; i += 2) {
            uint64_t vlo = float64_val(env->vfp.regs[i * 2]);
            uint64_t vhi = float64_val(env->vfp.regs[(i * 2) + 1]);
            cpu_fprintf(f, "q%02d=%016" PRIx64 ":%016" PRIx64 " ",
                        i, vhi, vlo);
            vlo = float64_val(env->vfp.regs[(i + 1) * 2]);
            vhi = float64_val(env->vfp.regs[((i + 1) * 2) + 1]);
            cpu_fprintf(f, "q%02d=%016" PRIx64 ":%016" PRIx64 "\n",
                        i + 1, vhi, vlo);
        }
        cpu_fprintf(f, "FPCR: %08x  FPSR: %08x\n",
                    vfp_get_fpcr(env), vfp_get_fpsr(env));
    }
}

void gen_a64_set_pc_im(uint64_t val)
{
    tcg_gen_movi_i64(cpu_pc, val);
}

/* Load the PC from a generic TCG variable.
 *
 * If address tagging is enabled via the TCR TBI bits, then loading
 * an address into the PC will clear out any tag in the it:
 *  + for EL2 and EL3 there is only one TBI bit, and if it is set
 *    then the address is zero-extended, clearing bits [63:56]
 *  + for EL0 and EL1, TBI0 controls addresses with bit 55 == 0
 *    and TBI1 controls addressses with bit 55 == 1.
 *    If the appropriate TBI bit is set for the address then
 *    the address is sign-extended from bit 55 into bits [63:56]
 *
 * We can avoid doing this for relative-branches, because the
 * PC + offset can never overflow into the tag bits (assuming
 * that virtual addresses are less than 56 bits wide, as they
 * are currently), but we must handle it for branch-to-register.
 */
static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src)
{

    if (s->current_el <= 1) {
        /* Test if NEITHER or BOTH TBI values are set.  If so, no need to
         * examine bit 55 of address, can just generate code.
         * If mixed, then test via generated code
         */
        if (s->tbi0 && s->tbi1) {
            TCGv_i64 tmp_reg = tcg_temp_new_i64();
            /* Both bits set, sign extension from bit 55 into [63:56] will
             * cover both cases
             */
            tcg_gen_shli_i64(tmp_reg, src, 8);
            tcg_gen_sari_i64(cpu_pc, tmp_reg, 8);
            tcg_temp_free_i64(tmp_reg);
        } else if (!s->tbi0 && !s->tbi1) {
            /* Neither bit set, just load it as-is */
            tcg_gen_mov_i64(cpu_pc, src);
        } else {
            TCGv_i64 tcg_tmpval = tcg_temp_new_i64();
            TCGv_i64 tcg_bit55  = tcg_temp_new_i64();
            TCGv_i64 tcg_zero   = tcg_const_i64(0);

            tcg_gen_andi_i64(tcg_bit55, src, (1ull << 55));

            if (s->tbi0) {
                /* tbi0==1, tbi1==0, so 0-fill upper byte if bit 55 = 0 */
                tcg_gen_andi_i64(tcg_tmpval, src,
                                 0x00FFFFFFFFFFFFFFull);
                tcg_gen_movcond_i64(TCG_COND_EQ, cpu_pc, tcg_bit55, tcg_zero,
                                    tcg_tmpval, src);
            } else {
                /* tbi0==0, tbi1==1, so 1-fill upper byte if bit 55 = 1 */
                tcg_gen_ori_i64(tcg_tmpval, src,
                                0xFF00000000000000ull);
                tcg_gen_movcond_i64(TCG_COND_NE, cpu_pc, tcg_bit55, tcg_zero,
                                    tcg_tmpval, src);
            }
            tcg_temp_free_i64(tcg_zero);
            tcg_temp_free_i64(tcg_bit55);
            tcg_temp_free_i64(tcg_tmpval);
        }
    } else {  /* EL > 1 */
        if (s->tbi0) {
            /* Force tag byte to all zero */
            tcg_gen_andi_i64(cpu_pc, src, 0x00FFFFFFFFFFFFFFull);
        } else {
            /* Load unmodified address */
            tcg_gen_mov_i64(cpu_pc, src);
        }
    }
}

typedef struct DisasCompare64 {
    TCGCond cond;
    TCGv_i64 value;
} DisasCompare64;

static void a64_test_cc(DisasCompare64 *c64, int cc)
{
    DisasCompare c32;

    arm_test_cc(&c32, cc);

    /* Sign-extend the 32-bit value so that the GE/LT comparisons work
       * properly.  The NE/EQ comparisons are also fine with this choice.  */
    c64->cond = c32.cond;
    c64->value = tcg_temp_new_i64();
    tcg_gen_ext_i32_i64(c64->value, c32.value);

    arm_free_cc(&c32);
}

static void a64_free_cc(DisasCompare64 *c64)
{
    tcg_temp_free_i64(c64->value);
}

static void gen_exception_internal(int excp)
{
    TCGv_i32 tcg_excp = tcg_const_i32(excp);

    assert(excp_is_internal(excp));
    gen_helper_exception_internal(cpu_env, tcg_excp);
    tcg_temp_free_i32(tcg_excp);
}

static void gen_exception(int excp, uint32_t syndrome, uint32_t target_el)
{
    TCGv_i32 tcg_excp = tcg_const_i32(excp);
    TCGv_i32 tcg_syn = tcg_const_i32(syndrome);
    TCGv_i32 tcg_el = tcg_const_i32(target_el);

    gen_helper_exception_with_syndrome(cpu_env, tcg_excp,
                                       tcg_syn, tcg_el);
    tcg_temp_free_i32(tcg_el);
    tcg_temp_free_i32(tcg_syn);
    tcg_temp_free_i32(tcg_excp);
}

static void gen_exception_internal_insn(DisasContext *s, int offset, int excp)
{
    gen_a64_set_pc_im(s->pc - offset);
    gen_exception_internal(excp);
    s->is_jmp = DISAS_EXC;
}

static void gen_exception_insn(DisasContext *s, int offset, int excp,
                               uint32_t syndrome, uint32_t target_el)
{
    gen_a64_set_pc_im(s->pc - offset);
    gen_exception(excp, syndrome, target_el);
    s->is_jmp = DISAS_EXC;
}

static void gen_ss_advance(DisasContext *s)
{
    /* If the singlestep state is Active-not-pending, advance to
     * Active-pending.
     */
    if (s->ss_active) {
        s->pstate_ss = 0;
        gen_helper_clear_pstate_ss(cpu_env);
    }
}

static void gen_step_complete_exception(DisasContext *s)
{
    /* We just completed step of an insn. Move from Active-not-pending
     * to Active-pending, and then also take the swstep exception.
     * This corresponds to making the (IMPDEF) choice to prioritize
     * swstep exceptions over asynchronous exceptions taken to an exception
     * level where debug is disabled. This choice has the advantage that
     * we do not need to maintain internal state corresponding to the
     * ISV/EX syndrome bits between completion of the step and generation
     * of the exception, and our syndrome information is always correct.
     */
    gen_ss_advance(s);
    gen_exception(EXCP_UDEF, syn_swstep(s->ss_same_el, 1, s->is_ldex),
                  default_exception_el(s));
    s->is_jmp = DISAS_EXC;
}

static inline bool use_goto_tb(DisasContext *s, int n, uint64_t dest)
{
    /* No direct tb linking with singlestep (either QEMU's or the ARM
     * debug architecture kind) or deterministic io
     */
    if (s->singlestep_enabled || s->ss_active || (s->tb->cflags & CF_LAST_IO)) {
        return false;
    }

#ifndef CONFIG_USER_ONLY
    /* Only link tbs from inside the same guest page */
    if ((s->tb->pc & TARGET_PAGE_MASK) != (dest & TARGET_PAGE_MASK)) {
        return false;
    }
#endif

    return true;
}

static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest)
{
    TranslationBlock *tb;

    tb = s->tb;
    if (use_goto_tb(s, n, dest)) {
        tcg_gen_goto_tb(n);
        gen_a64_set_pc_im(dest);
        tcg_gen_exit_tb((intptr_t)tb + n);
        s->is_jmp = DISAS_TB_JUMP;
    } else {
        gen_a64_set_pc_im(dest);
        if (s->ss_active) {
            gen_step_complete_exception(s);
        } else if (s->singlestep_enabled) {
            gen_exception_internal(EXCP_DEBUG);
        } else {
            tcg_gen_exit_tb(0);
            s->is_jmp = DISAS_TB_JUMP;
        }
    }
}

static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn)
{
    /* We don't need to save all of the syndrome so we mask and shift
     * out uneeded bits to help the sleb128 encoder do a better job.
     */
    syn &= ARM_INSN_START_WORD2_MASK;
    syn >>= ARM_INSN_START_WORD2_SHIFT;

    /* We check and clear insn_start_idx to catch multiple updates.  */
    assert(s->insn_start_idx != 0);
    tcg_set_insn_param(s->insn_start_idx, 2, syn);
    s->insn_start_idx = 0;
}

static void unallocated_encoding(DisasContext *s)
{
    /* Unallocated and reserved encodings are uncategorized */
    gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(),
                       default_exception_el(s));
}

#define unsupported_encoding(s, insn)                                    \
    do {                                                                 \
        qemu_log_mask(LOG_UNIMP,                                         \
                      "%s:%d: unsupported instruction encoding 0x%08x "  \
                      "at pc=%016" PRIx64 "\n",                          \
                      __FILE__, __LINE__, insn, s->pc - 4);              \
        unallocated_encoding(s);                                         \
    } while (0);

static void init_tmp_a64_array(DisasContext *s)
{
#ifdef CONFIG_DEBUG_TCG
    int i;
    for (i = 0; i < ARRAY_SIZE(s->tmp_a64); i++) {
        TCGV_UNUSED_I64(s->tmp_a64[i]);
    }
#endif
    s->tmp_a64_count = 0;
}

static void free_tmp_a64(DisasContext *s)
{
    int i;
    for (i = 0; i < s->tmp_a64_count; i++) {
        tcg_temp_free_i64(s->tmp_a64[i]);
    }
    init_tmp_a64_array(s);
}

static TCGv_i64 new_tmp_a64(DisasContext *s)
{
    assert(s->tmp_a64_count < TMP_A64_MAX);
    return s->tmp_a64[s->tmp_a64_count++] = tcg_temp_new_i64();
}

static TCGv_i64 new_tmp_a64_zero(DisasContext *s)
{
    TCGv_i64 t = new_tmp_a64(s);
    tcg_gen_movi_i64(t, 0);
    return t;
}

/*
 * Register access functions
 *
 * These functions are used for directly accessing a register in where
 * changes to the final register value are likely to be made. If you
 * need to use a register for temporary calculation (e.g. index type
 * operations) use the read_* form.
 *
 * B1.2.1 Register mappings
 *
 * In instruction register encoding 31 can refer to ZR (zero register) or
 * the SP (stack pointer) depending on context. In QEMU's case we map SP
 * to cpu_X[31] and ZR accesses to a temporary which can be discarded.
 * This is the point of the _sp forms.
 */
static TCGv_i64 cpu_reg(DisasContext *s, int reg)
{
    if (reg == 31) {
        return new_tmp_a64_zero(s);
    } else {
        return cpu_X[reg];
    }
}

/* register access for when 31 == SP */
static TCGv_i64 cpu_reg_sp(DisasContext *s, int reg)
{
    return cpu_X[reg];
}

/* read a cpu register in 32bit/64bit mode. Returns a TCGv_i64
 * representing the register contents. This TCGv is an auto-freed
 * temporary so it need not be explicitly freed, and may be modified.
 */
static TCGv_i64 read_cpu_reg(DisasContext *s, int reg, int sf)
{
    TCGv_i64 v = new_tmp_a64(s);
    if (reg != 31) {
        if (sf) {
            tcg_gen_mov_i64(v, cpu_X[reg]);
        } else {
            tcg_gen_ext32u_i64(v, cpu_X[reg]);
        }
    } else {
        tcg_gen_movi_i64(v, 0);
    }
    return v;
}

static TCGv_i64 read_cpu_reg_sp(DisasContext *s, int reg, int sf)
{
    TCGv_i64 v = new_tmp_a64(s);
    if (sf) {
        tcg_gen_mov_i64(v, cpu_X[reg]);
    } else {
        tcg_gen_ext32u_i64(v, cpu_X[reg]);
    }
    return v;
}

/* We should have at some point before trying to access an FP register
 * done the necessary access check, so assert that
 * (a) we did the check and
 * (b) we didn't then just plough ahead anyway if it failed.
 * Print the instruction pattern in the abort message so we can figure
 * out what we need to fix if a user encounters this problem in the wild.
 */
static inline void assert_fp_access_checked(DisasContext *s)
{
#ifdef CONFIG_DEBUG_TCG
    if (unlikely(!s->fp_access_checked || s->fp_excp_el)) {
        fprintf(stderr, "target-arm: FP access check missing for "
                "instruction 0x%08x\n", s->insn);
        abort();
    }
#endif
}

/* Return the offset into CPUARMState of an element of specified
 * size, 'element' places in from the least significant end of
 * the FP/vector register Qn.
 */
static inline int vec_reg_offset(DisasContext *s, int regno,
                                 int element, TCGMemOp size)
{
    int offs = 0;
#ifdef HOST_WORDS_BIGENDIAN
    /* This is complicated slightly because vfp.regs[2n] is
     * still the low half and  vfp.regs[2n+1] the high half
     * of the 128 bit vector, even on big endian systems.
     * Calculate the offset assuming a fully bigendian 128 bits,
     * then XOR to account for the order of the two 64 bit halves.
     */
    offs += (16 - ((element + 1) * (1 << size)));
    offs ^= 8;
#else
    offs += element * (1 << size);
#endif
    offs += offsetof(CPUARMState, vfp.regs[regno * 2]);
    assert_fp_access_checked(s);
    return offs;
}

/* Return the offset into CPUARMState of a slice (from
 * the least significant end) of FP register Qn (ie
 * Dn, Sn, Hn or Bn).
 * (Note that this is not the same mapping as for A32; see cpu.h)
 */
static inline int fp_reg_offset(DisasContext *s, int regno, TCGMemOp size)
{
    int offs = offsetof(CPUARMState, vfp.regs[regno * 2]);
#ifdef HOST_WORDS_BIGENDIAN
    offs += (8 - (1 << size));
#endif
    assert_fp_access_checked(s);
    return offs;
}

/* Offset of the high half of the 128 bit vector Qn */
static inline int fp_reg_hi_offset(DisasContext *s, int regno)
{
    assert_fp_access_checked(s);
    return offsetof(CPUARMState, vfp.regs[regno * 2 + 1]);
}

/* Convenience accessors for reading and writing single and double
 * FP registers. Writing clears the upper parts of the associated
 * 128 bit vector register, as required by the architecture.
 * Note that unlike the GP register accessors, the values returned
 * by the read functions must be manually freed.
 */
static TCGv_i64 read_fp_dreg(DisasContext *s, int reg)
{
    TCGv_i64 v = tcg_temp_new_i64();

    tcg_gen_ld_i64(v, cpu_env, fp_reg_offset(s, reg, MO_64));
    return v;
}

static TCGv_i32 read_fp_sreg(DisasContext *s, int reg)
{
    TCGv_i32 v = tcg_temp_new_i32();

    tcg_gen_ld_i32(v, cpu_env, fp_reg_offset(s, reg, MO_32));
    return v;
}

static void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v)
{
    TCGv_i64 tcg_zero = tcg_const_i64(0);

    tcg_gen_st_i64(v, cpu_env, fp_reg_offset(s, reg, MO_64));
    tcg_gen_st_i64(tcg_zero, cpu_env, fp_reg_hi_offset(s, reg));
    tcg_temp_free_i64(tcg_zero);
}

static void write_fp_sreg(DisasContext *s, int reg, TCGv_i32 v)
{
    TCGv_i64 tmp = tcg_temp_new_i64();

    tcg_gen_extu_i32_i64(tmp, v);
    write_fp_dreg(s, reg, tmp);
    tcg_temp_free_i64(tmp);
}

static TCGv_ptr get_fpstatus_ptr(void)
{
    TCGv_ptr statusptr = tcg_temp_new_ptr();
    int offset;

    /* In A64 all instructions (both FP and Neon) use the FPCR;
     * there is no equivalent of the A32 Neon "standard FPSCR value"
     * and all operations use vfp.fp_status.
     */
    offset = offsetof(CPUARMState, vfp.fp_status);
    tcg_gen_addi_ptr(statusptr, cpu_env, offset);
    return statusptr;
}

/* Set ZF and NF based on a 64 bit result. This is alas fiddlier
 * than the 32 bit equivalent.
 */
static inline void gen_set_NZ64(TCGv_i64 result)
{
    tcg_gen_extr_i64_i32(cpu_ZF, cpu_NF, result);
    tcg_gen_or_i32(cpu_ZF, cpu_ZF, cpu_NF);
}

/* Set NZCV as for a logical operation: NZ as per result, CV cleared. */
static inline void gen_logic_CC(int sf, TCGv_i64 result)
{
    if (sf) {
        gen_set_NZ64(result);
    } else {
        tcg_gen_extrl_i64_i32(cpu_ZF, result);
        tcg_gen_mov_i32(cpu_NF, cpu_ZF);
    }
    tcg_gen_movi_i32(cpu_CF, 0);
    tcg_gen_movi_i32(cpu_VF, 0);
}

/* dest = T0 + T1; compute C, N, V and Z flags */
static void gen_add_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    if (sf) {
        TCGv_i64 result, flag, tmp;
        result = tcg_temp_new_i64();
        flag = tcg_temp_new_i64();
        tmp = tcg_temp_new_i64();

        tcg_gen_movi_i64(tmp, 0);
        tcg_gen_add2_i64(result, flag, t0, tmp, t1, tmp);

        tcg_gen_extrl_i64_i32(cpu_CF, flag);

        gen_set_NZ64(result);

        tcg_gen_xor_i64(flag, result, t0);
        tcg_gen_xor_i64(tmp, t0, t1);
        tcg_gen_andc_i64(flag, flag, tmp);
        tcg_temp_free_i64(tmp);
        tcg_gen_extrh_i64_i32(cpu_VF, flag);

        tcg_gen_mov_i64(dest, result);
        tcg_temp_free_i64(result);
        tcg_temp_free_i64(flag);
    } else {
        /* 32 bit arithmetic */
        TCGv_i32 t0_32 = tcg_temp_new_i32();
        TCGv_i32 t1_32 = tcg_temp_new_i32();
        TCGv_i32 tmp = tcg_temp_new_i32();

        tcg_gen_movi_i32(tmp, 0);
        tcg_gen_extrl_i64_i32(t0_32, t0);
        tcg_gen_extrl_i64_i32(t1_32, t1);
        tcg_gen_add2_i32(cpu_NF, cpu_CF, t0_32, tmp, t1_32, tmp);
        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
        tcg_gen_xor_i32(tmp, t0_32, t1_32);
        tcg_gen_andc_i32(cpu_VF, cpu_VF, tmp);
        tcg_gen_extu_i32_i64(dest, cpu_NF);

        tcg_temp_free_i32(tmp);
        tcg_temp_free_i32(t0_32);
        tcg_temp_free_i32(t1_32);
    }
}

/* dest = T0 - T1; compute C, N, V and Z flags */
static void gen_sub_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    if (sf) {
        /* 64 bit arithmetic */
        TCGv_i64 result, flag, tmp;

        result = tcg_temp_new_i64();
        flag = tcg_temp_new_i64();
        tcg_gen_sub_i64(result, t0, t1);

        gen_set_NZ64(result);

        tcg_gen_setcond_i64(TCG_COND_GEU, flag, t0, t1);
        tcg_gen_extrl_i64_i32(cpu_CF, flag);

        tcg_gen_xor_i64(flag, result, t0);
        tmp = tcg_temp_new_i64();
        tcg_gen_xor_i64(tmp, t0, t1);
        tcg_gen_and_i64(flag, flag, tmp);
        tcg_temp_free_i64(tmp);
        tcg_gen_extrh_i64_i32(cpu_VF, flag);
        tcg_gen_mov_i64(dest, result);
        tcg_temp_free_i64(flag);
        tcg_temp_free_i64(result);
    } else {
        /* 32 bit arithmetic */
        TCGv_i32 t0_32 = tcg_temp_new_i32();
        TCGv_i32 t1_32 = tcg_temp_new_i32();
        TCGv_i32 tmp;

        tcg_gen_extrl_i64_i32(t0_32, t0);
        tcg_gen_extrl_i64_i32(t1_32, t1);
        tcg_gen_sub_i32(cpu_NF, t0_32, t1_32);
        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
        tcg_gen_setcond_i32(TCG_COND_GEU, cpu_CF, t0_32, t1_32);
        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
        tmp = tcg_temp_new_i32();
        tcg_gen_xor_i32(tmp, t0_32, t1_32);
        tcg_temp_free_i32(t0_32);
        tcg_temp_free_i32(t1_32);
        tcg_gen_and_i32(cpu_VF, cpu_VF, tmp);
        tcg_temp_free_i32(tmp);
        tcg_gen_extu_i32_i64(dest, cpu_NF);
    }
}

/* dest = T0 + T1 + CF; do not compute flags. */
static void gen_adc(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    TCGv_i64 flag = tcg_temp_new_i64();
    tcg_gen_extu_i32_i64(flag, cpu_CF);
    tcg_gen_add_i64(dest, t0, t1);
    tcg_gen_add_i64(dest, dest, flag);
    tcg_temp_free_i64(flag);

    if (!sf) {
        tcg_gen_ext32u_i64(dest, dest);
    }
}

/* dest = T0 + T1 + CF; compute C, N, V and Z flags. */
static void gen_adc_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    if (sf) {
        TCGv_i64 result, cf_64, vf_64, tmp;
        result = tcg_temp_new_i64();
        cf_64 = tcg_temp_new_i64();
        vf_64 = tcg_temp_new_i64();
        tmp = tcg_const_i64(0);

        tcg_gen_extu_i32_i64(cf_64, cpu_CF);
        tcg_gen_add2_i64(result, cf_64, t0, tmp, cf_64, tmp);
        tcg_gen_add2_i64(result, cf_64, result, cf_64, t1, tmp);
        tcg_gen_extrl_i64_i32(cpu_CF, cf_64);
        gen_set_NZ64(result);

        tcg_gen_xor_i64(vf_64, result, t0);
        tcg_gen_xor_i64(tmp, t0, t1);
        tcg_gen_andc_i64(vf_64, vf_64, tmp);
        tcg_gen_extrh_i64_i32(cpu_VF, vf_64);

        tcg_gen_mov_i64(dest, result);

        tcg_temp_free_i64(tmp);
        tcg_temp_free_i64(vf_64);
        tcg_temp_free_i64(cf_64);
        tcg_temp_free_i64(result);
    } else {
        TCGv_i32 t0_32, t1_32, tmp;
        t0_32 = tcg_temp_new_i32();
        t1_32 = tcg_temp_new_i32();
        tmp = tcg_const_i32(0);

        tcg_gen_extrl_i64_i32(t0_32, t0);
        tcg_gen_extrl_i64_i32(t1_32, t1);
        tcg_gen_add2_i32(cpu_NF, cpu_CF, t0_32, tmp, cpu_CF, tmp);
        tcg_gen_add2_i32(cpu_NF, cpu_CF, cpu_NF, cpu_CF, t1_32, tmp);

        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
        tcg_gen_xor_i32(tmp, t0_32, t1_32);
        tcg_gen_andc_i32(cpu_VF, cpu_VF, tmp);
        tcg_gen_extu_i32_i64(dest, cpu_NF);

        tcg_temp_free_i32(tmp);
        tcg_temp_free_i32(t1_32);
        tcg_temp_free_i32(t0_32);
    }
}

/*
 * Load/Store generators
 */

/*
 * Store from GPR register to memory.
 */
static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source,
                             TCGv_i64 tcg_addr, int size, int memidx,
                             bool iss_valid,
                             unsigned int iss_srt,
                             bool iss_sf, bool iss_ar)
{
    g_assert(size <= 3);
    tcg_gen_qemu_st_i64(source, tcg_addr, memidx, s->be_data + size);

    if (iss_valid) {
        uint32_t syn;

        syn = syn_data_abort_with_iss(0,
                                      size,
                                      false,
                                      iss_srt,
                                      iss_sf,
                                      iss_ar,
                                      0, 0, 0, 0, 0, false);
        disas_set_insn_syndrome(s, syn);
    }
}

static void do_gpr_st(DisasContext *s, TCGv_i64 source,
                      TCGv_i64 tcg_addr, int size,
                      bool iss_valid,
                      unsigned int iss_srt,
                      bool iss_sf, bool iss_ar)
{
    do_gpr_st_memidx(s, source, tcg_addr, size, get_mem_index(s),
                     iss_valid, iss_srt, iss_sf, iss_ar);
}

/*
 * Load from memory to GPR register
 */
static void do_gpr_ld_memidx(DisasContext *s,
                             TCGv_i64 dest, TCGv_i64 tcg_addr,
                             int size, bool is_signed,
                             bool extend, int memidx,
                             bool iss_valid, unsigned int iss_srt,
                             bool iss_sf, bool iss_ar)
{
    TCGMemOp memop = s->be_data + size;

    g_assert(size <= 3);

    if (is_signed) {
        memop += MO_SIGN;
    }

    tcg_gen_qemu_ld_i64(dest, tcg_addr, memidx, memop);

    if (extend && is_signed) {
        g_assert(size < 3);
        tcg_gen_ext32u_i64(dest, dest);
    }

    if (iss_valid) {
        uint32_t syn;

        syn = syn_data_abort_with_iss(0,
                                      size,
                                      is_signed,
                                      iss_srt,
                                      iss_sf,
                                      iss_ar,
                                      0, 0, 0, 0, 0, false);
        disas_set_insn_syndrome(s, syn);
    }
}

static void do_gpr_ld(DisasContext *s,
                      TCGv_i64 dest, TCGv_i64 tcg_addr,
                      int size, bool is_signed, bool extend,
                      bool iss_valid, unsigned int iss_srt,
                      bool iss_sf, bool iss_ar)
{
    do_gpr_ld_memidx(s, dest, tcg_addr, size, is_signed, extend,
                     get_mem_index(s),
                     iss_valid, iss_srt, iss_sf, iss_ar);
}

/*
 * Store from FP register to memory
 */
static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
{
    /* This writes the bottom N bits of a 128 bit wide vector to memory */
    TCGv_i64 tmp = tcg_temp_new_i64();
    tcg_gen_ld_i64(tmp, cpu_env, fp_reg_offset(s, srcidx, MO_64));
    if (size < 4) {
        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s),
                            s->be_data + size);
    } else {
        bool be = s->be_data == MO_BE;
        TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();

        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
        tcg_gen_qemu_st_i64(tmp, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
                            s->be_data | MO_Q);
        tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx));
        tcg_gen_qemu_st_i64(tmp, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
                            s->be_data | MO_Q);
        tcg_temp_free_i64(tcg_hiaddr);
    }

    tcg_temp_free_i64(tmp);
}

/*
 * Load from memory to FP register
 */
static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
{
    /* This always zero-extends and writes to a full 128 bit wide vector */
    TCGv_i64 tmplo = tcg_temp_new_i64();
    TCGv_i64 tmphi;

    if (size < 4) {
        TCGMemOp memop = s->be_data + size;
        tmphi = tcg_const_i64(0);
        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
    } else {
        bool be = s->be_data == MO_BE;
        TCGv_i64 tcg_hiaddr;

        tmphi = tcg_temp_new_i64();
        tcg_hiaddr = tcg_temp_new_i64();

        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
        tcg_gen_qemu_ld_i64(tmplo, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
                            s->be_data | MO_Q);
        tcg_gen_qemu_ld_i64(tmphi, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
                            s->be_data | MO_Q);
        tcg_temp_free_i64(tcg_hiaddr);
    }

    tcg_gen_st_i64(tmplo, cpu_env, fp_reg_offset(s, destidx, MO_64));
    tcg_gen_st_i64(tmphi, cpu_env, fp_reg_hi_offset(s, destidx));

    tcg_temp_free_i64(tmplo);
    tcg_temp_free_i64(tmphi);
}

/*
 * Vector load/store helpers.
 *
 * The principal difference between this and a FP load is that we don't
 * zero extend as we are filling a partial chunk of the vector register.
 * These functions don't support 128 bit loads/stores, which would be
 * normal load/store operations.
 *
 * The _i32 versions are useful when operating on 32 bit quantities
 * (eg for floating point single or using Neon helper functions).
 */

/* Get value of an element within a vector register */
static void read_vec_element(DisasContext *s, TCGv_i64 tcg_dest, int srcidx,
                             int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(s, srcidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_ld8u_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_ld16u_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_32:
        tcg_gen_ld32u_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_8|MO_SIGN:
        tcg_gen_ld8s_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16|MO_SIGN:
        tcg_gen_ld16s_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_32|MO_SIGN:
        tcg_gen_ld32s_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_64:
    case MO_64|MO_SIGN:
        tcg_gen_ld_i64(tcg_dest, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

static void read_vec_element_i32(DisasContext *s, TCGv_i32 tcg_dest, int srcidx,
                                 int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(s, srcidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_ld8u_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_ld16u_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_8|MO_SIGN:
        tcg_gen_ld8s_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16|MO_SIGN:
        tcg_gen_ld16s_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_32:
    case MO_32|MO_SIGN:
        tcg_gen_ld_i32(tcg_dest, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

/* Set value of an element within a vector register */
static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
                              int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(s, destidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_st8_i64(tcg_src, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_st16_i64(tcg_src, cpu_env, vect_off);
        break;
    case MO_32:
        tcg_gen_st32_i64(tcg_src, cpu_env, vect_off);
        break;
    case MO_64:
        tcg_gen_st_i64(tcg_src, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src,
                                  int destidx, int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(s, destidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_st8_i32(tcg_src, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_st16_i32(tcg_src, cpu_env, vect_off);
        break;
    case MO_32:
        tcg_gen_st_i32(tcg_src, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

/* Clear the high 64 bits of a 128 bit vector (in general non-quad
 * vector ops all need to do this).
 */
static void clear_vec_high(DisasContext *s, int rd)
{
    TCGv_i64 tcg_zero = tcg_const_i64(0);

    write_vec_element(s, tcg_zero, rd, 1, MO_64);
    tcg_temp_free_i64(tcg_zero);
}

/* Store from vector register to memory */
static void do_vec_st(DisasContext *s, int srcidx, int element,
                      TCGv_i64 tcg_addr, int size)
{
    TCGMemOp memop = s->be_data + size;
    TCGv_i64 tcg_tmp = tcg_temp_new_i64();

    read_vec_element(s, tcg_tmp, srcidx, element, size);
    tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);

    tcg_temp_free_i64(tcg_tmp);
}

/* Load from memory to vector register */
static void do_vec_ld(DisasContext *s, int destidx, int element,
                      TCGv_i64 tcg_addr, int size)
{
    TCGMemOp memop = s->be_data + size;
    TCGv_i64 tcg_tmp = tcg_temp_new_i64();

    tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);
    write_vec_element(s, tcg_tmp, destidx, element, size);

    tcg_temp_free_i64(tcg_tmp);
}

/* Check that FP/Neon access is enabled. If it is, return
 * true. If not, emit code to generate an appropriate exception,
 * and return false; the caller should not emit any code for
 * the instruction. Note that this check must happen after all
 * unallocated-encoding checks (otherwise the syndrome information
 * for the resulting exception will be incorrect).
 */
static inline bool fp_access_check(DisasContext *s)
{
    assert(!s->fp_access_checked);
    s->fp_access_checked = true;

    if (!s->fp_excp_el) {
        return true;
    }

    gen_exception_insn(s, 4, EXCP_UDEF, syn_fp_access_trap(1, 0xe, false),
                       s->fp_excp_el);
    return false;
}

/*
 * This utility function is for doing register extension with an
 * optional shift. You will likely want to pass a temporary for the
 * destination register. See DecodeRegExtend() in the ARM ARM.
 */
static void ext_and_shift_reg(TCGv_i64 tcg_out, TCGv_i64 tcg_in,
                              int option, unsigned int shift)
{
    int extsize = extract32(option, 0, 2);
    bool is_signed = extract32(option, 2, 1);

    if (is_signed) {
        switch (extsize) {
        case 0:
            tcg_gen_ext8s_i64(tcg_out, tcg_in);
            break;
        case 1:
            tcg_gen_ext16s_i64(tcg_out, tcg_in);
            break;
        case 2:
            tcg_gen_ext32s_i64(tcg_out, tcg_in);
            break;
        case 3:
            tcg_gen_mov_i64(tcg_out, tcg_in);
            break;
        }
    } else {
        switch (extsize) {
        case 0:
            tcg_gen_ext8u_i64(tcg_out, tcg_in);
            break;
        case 1:
            tcg_gen_ext16u_i64(tcg_out, tcg_in);
            break;
        case 2:
            tcg_gen_ext32u_i64(tcg_out, tcg_in);
            break;
        case 3:
            tcg_gen_mov_i64(tcg_out, tcg_in);
            break;
        }
    }

    if (shift) {
        tcg_gen_shli_i64(tcg_out, tcg_out, shift);
    }
}

static inline void gen_check_sp_alignment(DisasContext *s)
{
    /* The AArch64 architecture mandates that (if enabled via PSTATE
     * or SCTLR bits) there is a check that SP is 16-aligned on every
     * SP-relative load or store (with an exception generated if it is not).
     * In line with general QEMU practice regarding misaligned accesses,
     * we omit these checks for the sake of guest program performance.
     * This function is provided as a hook so we can more easily add these
     * checks in future (possibly as a "favour catching guest program bugs
     * over speed" user selectable option).
     */
}

/*
 * This provides a simple table based table lookup decoder. It is
 * intended to be used when the relevant bits for decode are too
 * awkwardly placed and switch/if based logic would be confusing and
 * deeply nested. Since it's a linear search through the table, tables
 * should be kept small.
 *
 * It returns the first handler where insn & mask == pattern, or
 * NULL if there is no match.
 * The table is terminated by an empty mask (i.e. 0)
 */
static inline AArch64DecodeFn *lookup_disas_fn(const AArch64DecodeTable *table,
                                               uint32_t insn)
{
    const AArch64DecodeTable *tptr = table;

    while (tptr->mask) {
        if ((insn & tptr->mask) == tptr->pattern) {
            return tptr->disas_fn;
        }
        tptr++;
    }
    return NULL;
}

/*
 * the instruction disassembly implemented here matches
 * the instruction encoding classifications in chapter 3 (C3)
 * of the ARM Architecture Reference Manual (DDI0487A_a)
 */

/* C3.2.7 Unconditional branch (immediate)
 *   31  30       26 25                                  0
 * +----+-----------+-------------------------------------+
 * | op | 0 0 1 0 1 |                 imm26               |
 * +----+-----------+-------------------------------------+
 */
static void disas_uncond_b_imm(DisasContext *s, uint32_t insn)
{
    uint64_t addr = s->pc + sextract32(insn, 0, 26) * 4 - 4;

    if (insn & (1U << 31)) {
        /* C5.6.26 BL Branch with link */
        tcg_gen_movi_i64(cpu_reg(s, 30), s->pc);
    }

    /* C5.6.20 B Branch / C5.6.26 BL Branch with link */
    gen_goto_tb(s, 0, addr);
}

/* C3.2.1 Compare & branch (immediate)
 *   31  30         25  24  23                  5 4      0
 * +----+-------------+----+---------------------+--------+
 * | sf | 0 1 1 0 1 0 | op |         imm19       |   Rt   |
 * +----+-------------+----+---------------------+--------+
 */
static void disas_comp_b_imm(DisasContext *s, uint32_t insn)
{
    unsigned int sf, op, rt;
    uint64_t addr;
    TCGLabel *label_match;
    TCGv_i64 tcg_cmp;

    sf = extract32(insn, 31, 1);
    op = extract32(insn, 24, 1); /* 0: CBZ; 1: CBNZ */
    rt = extract32(insn, 0, 5);
    addr = s->pc + sextract32(insn, 5, 19) * 4 - 4;

    tcg_cmp = read_cpu_reg(s, rt, sf);
    label_match = gen_new_label();

    tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ,
                        tcg_cmp, 0, label_match);

    gen_goto_tb(s, 0, s->pc);
    gen_set_label(label_match);
    gen_goto_tb(s, 1, addr);
}

/* C3.2.5 Test & branch (immediate)
 *   31  30         25  24  23   19 18          5 4    0
 * +----+-------------+----+-------+-------------+------+
 * | b5 | 0 1 1 0 1 1 | op |  b40  |    imm14    |  Rt  |
 * +----+-------------+----+-------+-------------+------+
 */
static void disas_test_b_imm(DisasContext *s, uint32_t insn)
{
    unsigned int bit_pos, op, rt;
    uint64_t addr;
    TCGLabel *label_match;
    TCGv_i64 tcg_cmp;

    bit_pos = (extract32(insn, 31, 1) << 5) | extract32(insn, 19, 5);
    op = extract32(insn, 24, 1); /* 0: TBZ; 1: TBNZ */
    addr = s->pc + sextract32(insn, 5, 14) * 4 - 4;
    rt = extract32(insn, 0, 5);

    tcg_cmp = tcg_temp_new_i64();
    tcg_gen_andi_i64(tcg_cmp, cpu_reg(s, rt), (1ULL << bit_pos));
    label_match = gen_new_label();
    tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ,
                        tcg_cmp, 0, label_match);
    tcg_temp_free_i64(tcg_cmp);
    gen_goto_tb(s, 0, s->pc);
    gen_set_label(label_match);
    gen_goto_tb(s, 1, addr);
}

/* C3.2.2 / C5.6.19 Conditional branch (immediate)
 *  31           25  24  23                  5   4  3    0
 * +---------------+----+---------------------+----+------+
 * | 0 1 0 1 0 1 0 | o1 |         imm19       | o0 | cond |
 * +---------------+----+---------------------+----+------+
 */
static void disas_cond_b_imm(DisasContext *s, uint32_t insn)
{
    unsigned int cond;
    uint64_t addr;

    if ((insn & (1 << 4)) || (insn & (1 << 24))) {
        unallocated_encoding(s);
        return;
    }
    addr = s->pc + sextract32(insn, 5, 19) * 4 - 4;
    cond = extract32(insn, 0, 4);

    if (cond < 0x0e) {
        /* genuinely conditional branches */
        TCGLabel *label_match = gen_new_label();
        arm_gen_test_cc(cond, label_match);
        gen_goto_tb(s, 0, s->pc);
        gen_set_label(label_match);
        gen_goto_tb(s, 1, addr);
    } else {
        /* 0xe and 0xf are both "always" conditions */
        gen_goto_tb(s, 0, addr);
    }
}

/* C5.6.68 HINT */
static void handle_hint(DisasContext *s, uint32_t insn,
                        unsigned int op1, unsigned int op2, unsigned int crm)
{
    unsigned int selector = crm << 3 | op2;

    if (op1 != 3) {
        unallocated_encoding(s);
        return;
    }

    switch (selector) {
    case 0: /* NOP */
        return;
    case 3: /* WFI */
        s->is_jmp = DISAS_WFI;
        return;
    case 1: /* YIELD */
        s->is_jmp = DISAS_YIELD;
        return;
    case 2: /* WFE */
        s->is_jmp = DISAS_WFE;
        return;
    case 4: /* SEV */
        gen_helper_sev(cpu_env);
        return;
    case 5: /* SEVL */
        gen_helper_sevl(cpu_env);
        return;
    default:
        /* default specified as NOP equivalent */
        return;
    }
}

static void gen_clrex(DisasContext *s, uint32_t insn)
{
    tcg_gen_movi_i64(cpu_exclusive_addr, -1);
    gen_helper_sev(cpu_env);
}

/* CLREX, DSB, DMB, ISB */
static void handle_sync(DisasContext *s, uint32_t insn,
                        unsigned int op1, unsigned int op2, unsigned int crm)
{
    TCGBar bar;

    if (op1 != 3) {
        unallocated_encoding(s);
        return;
    }

    switch (op2) {
    case 2: /* CLREX */
        gen_clrex(s, insn);
        return;
    case 4: /* DSB */
    case 5: /* DMB */
        switch (crm & 3) {
        case 1: /* MBReqTypes_Reads */
            bar = TCG_BAR_SC | TCG_MO_LD_LD | TCG_MO_LD_ST;
            break;
        case 2: /* MBReqTypes_Writes */
            bar = TCG_BAR_SC | TCG_MO_ST_ST;
            break;
        default: /* MBReqTypes_All */
            bar = TCG_BAR_SC | TCG_MO_ALL;
            break;
        }
        tcg_gen_mb(bar);
        return;
    case 6: /* ISB */
        /* We need to break the TB after this insn to execute
         * a self-modified code correctly and also to take
         * any pending interrupts immediately.
         */
        s->is_jmp = DISAS_UPDATE;
        return;
    default:
        unallocated_encoding(s);
        return;
    }
}

/* C5.6.130 MSR (immediate) - move immediate to processor state field */
static void handle_msr_i(DisasContext *s, uint32_t insn,
                         unsigned int op1, unsigned int op2, unsigned int crm)
{
    int op = op1 << 3 | op2;
    switch (op) {
    case 0x05: /* SPSel */
        if (s->current_el == 0) {
            unallocated_encoding(s);
            return;
        }
        /* fall through */
    case 0x1e: /* DAIFSet */
    case 0x1f: /* DAIFClear */
    {
        TCGv_i32 tcg_imm = tcg_const_i32(crm);
        TCGv_i32 tcg_op = tcg_const_i32(op);
        gen_a64_set_pc_im(s->pc - 4);
        gen_helper_msr_i_pstate(cpu_env, tcg_op, tcg_imm);
        tcg_temp_free_i32(tcg_imm);
        tcg_temp_free_i32(tcg_op);
        s->is_jmp = DISAS_UPDATE;
        break;
    }
    default:
        unallocated_encoding(s);
        return;
    }
}

static void gen_get_nzcv(TCGv_i64 tcg_rt)
{
    TCGv_i32 tmp = tcg_temp_new_i32();
    TCGv_i32 nzcv = tcg_temp_new_i32();

    /* build bit 31, N */
    tcg_gen_andi_i32(nzcv, cpu_NF, (1U << 31));
    /* build bit 30, Z */
    tcg_gen_setcondi_i32(TCG_COND_EQ, tmp, cpu_ZF, 0);
    tcg_gen_deposit_i32(nzcv, nzcv, tmp, 30, 1);
    /* build bit 29, C */
    tcg_gen_deposit_i32(nzcv, nzcv, cpu_CF, 29, 1);
    /* build bit 28, V */
    tcg_gen_shri_i32(tmp, cpu_VF, 31);
    tcg_gen_deposit_i32(nzcv, nzcv, tmp, 28, 1);
    /* generate result */
    tcg_gen_extu_i32_i64(tcg_rt, nzcv);

    tcg_temp_free_i32(nzcv);
    tcg_temp_free_i32(tmp);
}

static void gen_set_nzcv(TCGv_i64 tcg_rt)

{
    TCGv_i32 nzcv = tcg_temp_new_i32();

    /* take NZCV from R[t] */
    tcg_gen_extrl_i64_i32(nzcv, tcg_rt);

    /* bit 31, N */
    tcg_gen_andi_i32(cpu_NF, nzcv, (1U << 31));
    /* bit 30, Z */
    tcg_gen_andi_i32(cpu_ZF, nzcv, (1 << 30));
    tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_ZF, cpu_ZF, 0);
    /* bit 29, C */
    tcg_gen_andi_i32(cpu_CF, nzcv, (1 << 29));
    tcg_gen_shri_i32(cpu_CF, cpu_CF, 29);
    /* bit 28, V */
    tcg_gen_andi_i32(cpu_VF, nzcv, (1 << 28));
    tcg_gen_shli_i32(cpu_VF, cpu_VF, 3);
    tcg_temp_free_i32(nzcv);
}

/* C5.6.129 MRS - move from system register
 * C5.6.131 MSR (register) - move to system register
 * C5.6.204 SYS
 * C5.6.205 SYSL
 * These are all essentially the same insn in 'read' and 'write'
 * versions, with varying op0 fields.
 */
static void handle_sys(DisasContext *s, uint32_t insn, bool isread,
                       unsigned int op0, unsigned int op1, unsigned int op2,
                       unsigned int crn, unsigned int crm, unsigned int rt)
{
    const ARMCPRegInfo *ri;
    TCGv_i64 tcg_rt;

    ri = get_arm_cp_reginfo(s->cp_regs,
                            ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP,
                                               crn, crm, op0, op1, op2));

    if (!ri) {
        /* Unknown register; this might be a guest error or a QEMU
         * unimplemented feature.
         */
        qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch64 "
                      "system register op0:%d op1:%d crn:%d crm:%d op2:%d\n",
                      isread ? "read" : "write", op0, op1, crn, crm, op2);
        unallocated_encoding(s);
        return;
    }

    /* Check access permissions */
    if (!cp_access_ok(s->current_el, ri, isread)) {
        unallocated_encoding(s);
        return;
    }

    if (ri->accessfn) {
        /* Emit code to perform further access permissions checks at
         * runtime; this may result in an exception.
         */
        TCGv_ptr tmpptr;
        TCGv_i32 tcg_syn, tcg_isread;
        uint32_t syndrome;

        gen_a64_set_pc_im(s->pc - 4);
        tmpptr = tcg_const_ptr(ri);
        syndrome = syn_aa64_sysregtrap(op0, op1, op2, crn, crm, rt, isread);
        tcg_syn = tcg_const_i32(syndrome);
        tcg_isread = tcg_const_i32(isread);
        gen_helper_access_check_cp_reg(cpu_env, tmpptr, tcg_syn, tcg_isread);
        tcg_temp_free_ptr(tmpptr);
        tcg_temp_free_i32(tcg_syn);
        tcg_temp_free_i32(tcg_isread);
    }

    /* Handle special cases first */
    switch (ri->type & ~(ARM_CP_FLAG_MASK & ~ARM_CP_SPECIAL)) {
    case ARM_CP_NOP:
        return;
    case ARM_CP_NZCV:
        tcg_rt = cpu_reg(s, rt);
        if (isread) {
            gen_get_nzcv(tcg_rt);
        } else {
            gen_set_nzcv(tcg_rt);
        }
        return;
    case ARM_CP_CURRENTEL:
        /* Reads as current EL value from pstate, which is
         * guaranteed to be constant by the tb flags.
         */
        tcg_rt = cpu_reg(s, rt);
        tcg_gen_movi_i64(tcg_rt, s->current_el << 2);
        return;
    case ARM_CP_DC_ZVA:
        /* Writes clear the aligned block of memory which rt points into. */
        tcg_rt = cpu_reg(s, rt);
        gen_helper_dc_zva(cpu_env, tcg_rt);
        return;
    default:
        break;
    }

    if ((s->tb->cflags & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) {
        gen_io_start();
    }

    tcg_rt = cpu_reg(s, rt);

    if (isread) {
        if (ri->type & ARM_CP_CONST) {
            tcg_gen_movi_i64(tcg_rt, ri->resetvalue);
        } else if (ri->readfn) {
            TCGv_ptr tmpptr;
            tmpptr = tcg_const_ptr(ri);
            gen_helper_get_cp_reg64(tcg_rt, cpu_env, tmpptr);
            tcg_temp_free_ptr(tmpptr);
        } else {
            tcg_gen_ld_i64(tcg_rt, cpu_env, ri->fieldoffset);
        }
    } else {
        if (ri->type & ARM_CP_CONST) {
            /* If not forbidden by access permissions, treat as WI */
            return;
        } else if (ri->writefn) {
            TCGv_ptr tmpptr;
            tmpptr = tcg_const_ptr(ri);
            gen_helper_set_cp_reg64(cpu_env, tmpptr, tcg_rt);
            tcg_temp_free_ptr(tmpptr);
        } else {
            tcg_gen_st_i64(tcg_rt, cpu_env, ri->fieldoffset);
        }
    }

    if ((s->tb->cflags & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) {
        /* I/O operations must end the TB here (whether read or write) */
        gen_io_end();
        s->is_jmp = DISAS_UPDATE;
    } else if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) {
        /* We default to ending the TB on a coprocessor register write,
         * but allow this to be suppressed by the register definition
         * (usually only necessary to work around guest bugs).
         */
        s->is_jmp = DISAS_UPDATE;
    }
}

/* C3.2.4 System
 *  31                 22 21  20 19 18 16 15   12 11    8 7   5 4    0
 * +---------------------+---+-----+-----+-------+-------+-----+------+
 * | 1 1 0 1 0 1 0 1 0 0 | L | op0 | op1 |  CRn  |  CRm  | op2 |  Rt  |
 * +---------------------+---+-----+-----+-------+-------+-----+------+
 */
static void disas_system(DisasContext *s, uint32_t insn)
{
    unsigned int l, op0, op1, crn, crm, op2, rt;
    l = extract32(insn, 21, 1);
    op0 = extract32(insn, 19, 2);
    op1 = extract32(insn, 16, 3);
    crn = extract32(insn, 12, 4);
    crm = extract32(insn, 8, 4);
    op2 = extract32(insn, 5, 3);
    rt = extract32(insn, 0, 5);

    if (op0 == 0) {
        if (l || rt != 31) {
            unallocated_encoding(s);
            return;
        }
        switch (crn) {
        case 2: /* C5.6.68 HINT */
            handle_hint(s, insn, op1, op2, crm);
            break;
        case 3: /* CLREX, DSB, DMB, ISB */
            handle_sync(s, insn, op1, op2, crm);
            break;
        case 4: /* C5.6.130 MSR (immediate) */
            handle_msr_i(s, insn, op1, op2, crm);
            break;
        default:
            unallocated_encoding(s);
            break;
        }
        return;
    }
    handle_sys(s, insn, l, op0, op1, op2, crn, crm, rt);
}

/* C3.2.3 Exception generation
 *
 *  31             24 23 21 20                     5 4   2 1  0
 * +-----------------+-----+------------------------+-----+----+
 * | 1 1 0 1 0 1 0 0 | opc |          imm16         | op2 | LL |
 * +-----------------------+------------------------+----------+
 */
static void disas_exc(DisasContext *s, uint32_t insn)
{
    int opc = extract32(insn, 21, 3);
    int op2_ll = extract32(insn, 0, 5);
    int imm16 = extract32(insn, 5, 16);
    TCGv_i32 tmp;

    switch (opc) {
    case 0:
        /* For SVC, HVC and SMC we advance the single-step state
         * machine before taking the exception. This is architecturally
         * mandated, to ensure that single-stepping a system call
         * instruction works properly.
         */
        switch (op2_ll) {
        case 1:                                                     /* SVC */
            gen_ss_advance(s);
            gen_exception_insn(s, 0, EXCP_SWI, syn_aa64_svc(imm16),
                               default_exception_el(s));
            break;
        case 2:                                                     /* HVC */
            if (s->current_el == 0) {
                unallocated_encoding(s);
                break;
            }
            /* The pre HVC helper handles cases when HVC gets trapped
             * as an undefined insn by runtime configuration.
             */
            gen_a64_set_pc_im(s->pc - 4);
            gen_helper_pre_hvc(cpu_env);
            gen_ss_advance(s);
            gen_exception_insn(s, 0, EXCP_HVC, syn_aa64_hvc(imm16), 2);
            break;
        case 3:                                                     /* SMC */
            if (s->current_el == 0) {
                unallocated_encoding(s);
                break;
            }
            gen_a64_set_pc_im(s->pc - 4);
            tmp = tcg_const_i32(syn_aa64_smc(imm16));
            gen_helper_pre_smc(cpu_env, tmp);
            tcg_temp_free_i32(tmp);
            gen_ss_advance(s);
            gen_exception_insn(s, 0, EXCP_SMC, syn_aa64_smc(imm16), 3);
            break;
        default:
            unallocated_encoding(s);
            break;
        }
        break;
    case 1:
        if (op2_ll != 0) {
            unallocated_encoding(s);
            break;
        }
        /* BRK */
        gen_exception_insn(s, 4, EXCP_BKPT, syn_aa64_bkpt(imm16),
                           default_exception_el(s));
        break;
    case 2:
        if (op2_ll != 0) {
            unallocated_encoding(s);
            break;
        }
        /* HLT. This has two purposes.
         * Architecturally, it is an external halting debug instruction.
         * Since QEMU doesn't implement external debug, we treat this as
         * it is required for halting debug disabled: it will UNDEF.
         * Secondly, "HLT 0xf000" is the A64 semihosting syscall instruction.
         */
        if (semihosting_enabled() && imm16 == 0xf000) {
#ifndef CONFIG_USER_ONLY
            /* In system mode, don't allow userspace access to semihosting,
             * to provide some semblance of security (and for consistency
             * with our 32-bit semihosting).
             */
            if (s->current_el == 0) {
                unsupported_encoding(s, insn);
                break;
            }
#endif
            gen_exception_internal_insn(s, 0, EXCP_SEMIHOST);
        } else {
            unsupported_encoding(s, insn);
        }
        break;
    case 5:
        if (op2_ll < 1 || op2_ll > 3) {
            unallocated_encoding(s);
            break;
        }
        /* DCPS1, DCPS2, DCPS3 */
        unsupported_encoding(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

/* C3.2.7 Unconditional branch (register)
 *  31           25 24   21 20   16 15   10 9    5 4     0
 * +---------------+-------+-------+-------+------+-------+
 * | 1 1 0 1 0 1 1 |  opc  |  op2  |  op3  |  Rn  |  op4  |
 * +---------------+-------+-------+-------+------+-------+
 */
static void disas_uncond_b_reg(DisasContext *s, uint32_t insn)
{
    unsigned int opc, op2, op3, rn, op4;

    opc = extract32(insn, 21, 4);
    op2 = extract32(insn, 16, 5);
    op3 = extract32(insn, 10, 6);
    rn = extract32(insn, 5, 5);
    op4 = extract32(insn, 0, 5);

    if (op4 != 0x0 || op3 != 0x0 || op2 != 0x1f) {
        unallocated_encoding(s);
        return;
    }

    switch (opc) {
    case 0: /* BR */
    case 1: /* BLR */
    case 2: /* RET */
        gen_a64_set_pc(s, cpu_reg(s, rn));
        /* BLR also needs to load return address */
        if (opc == 1) {
            tcg_gen_movi_i64(cpu_reg(s, 30), s->pc);
        }
        break;
    case 4: /* ERET */
        if (s->current_el == 0) {
            unallocated_encoding(s);
            return;
        }
        gen_helper_exception_return(cpu_env);
        s->is_jmp = DISAS_JUMP;
        return;
    case 5: /* DRPS */
        if (rn != 0x1f) {
            unallocated_encoding(s);
        } else {
            unsupported_encoding(s, insn);
        }
        return;
    default:
        unallocated_encoding(s);
        return;
    }

    s->is_jmp = DISAS_JUMP;
}

/* C3.2 Branches, exception generating and system instructions */
static void disas_b_exc_sys(DisasContext *s, uint32_t insn)
{
    switch (extract32(insn, 25, 7)) {
    case 0x0a: case 0x0b:
    case 0x4a: case 0x4b: /* Unconditional branch (immediate) */
        disas_uncond_b_imm(s, insn);
        break;
    case 0x1a: case 0x5a: /* Compare & branch (immediate) */
        disas_comp_b_imm(s, insn);
        break;
    case 0x1b: case 0x5b: /* Test & branch (immediate) */
        disas_test_b_imm(s, insn);
        break;
    case 0x2a: /* Conditional branch (immediate) */
        disas_cond_b_imm(s, insn);
        break;
    case 0x6a: /* Exception generation / System */
        if (insn & (1 << 24)) {
            disas_system(s, insn);
        } else {
            disas_exc(s, insn);
        }
        break;
    case 0x6b: /* Unconditional branch (register) */
        disas_uncond_b_reg(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

/*
 * Load/Store exclusive instructions are implemented by remembering
 * the value/address loaded, and seeing if these are the same
 * when the store is performed. This is not actually the architecturally
 * mandated semantics, but it works for typical guest code sequences
 * and avoids having to monitor regular stores.
 *
 * The store exclusive uses the atomic cmpxchg primitives to avoid
 * races in multi-threaded linux-user and when MTTCG softmmu is
 * enabled.
 */
static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                               TCGv_i64 addr, int size, bool is_pair)
{
    TCGv_i64 tmp = tcg_temp_new_i64();
    TCGMemOp memop = s->be_data + size;

    g_assert(size <= 3);
    tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), memop);

    if (is_pair) {
        TCGv_i64 addr2 = tcg_temp_new_i64();
        TCGv_i64 hitmp = tcg_temp_new_i64();

        g_assert(size >= 2);
        tcg_gen_addi_i64(addr2, addr, 1 << size);
        tcg_gen_qemu_ld_i64(hitmp, addr2, get_mem_index(s), memop);
        tcg_temp_free_i64(addr2);
        tcg_gen_mov_i64(cpu_exclusive_high, hitmp);
        tcg_gen_mov_i64(cpu_reg(s, rt2), hitmp);
        tcg_temp_free_i64(hitmp);
    }

    tcg_gen_mov_i64(cpu_exclusive_val, tmp);
    tcg_gen_mov_i64(cpu_reg(s, rt), tmp);

    tcg_temp_free_i64(tmp);
    tcg_gen_mov_i64(cpu_exclusive_addr, addr);
}

static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
                                TCGv_i64 inaddr, int size, int is_pair)
{
    /* if (env->exclusive_addr == addr && env->exclusive_val == [addr]
     *     && (!is_pair || env->exclusive_high == [addr + datasize])) {
     *     [addr] = {Rt};
     *     if (is_pair) {
     *         [addr + datasize] = {Rt2};
     *     }
     *     {Rd} = 0;
     * } else {
     *     {Rd} = 1;
     * }
     * env->exclusive_addr = -1;
     */
    TCGLabel *fail_label = gen_new_label();
    TCGLabel *done_label = gen_new_label();
    TCGv_i64 addr = tcg_temp_local_new_i64();
    TCGv_i64 tmp;

    /* Copy input into a local temp so it is not trashed when the
     * basic block ends at the branch insn.
     */
    tcg_gen_mov_i64(addr, inaddr);
    tcg_gen_brcond_i64(TCG_COND_NE, addr, cpu_exclusive_addr, fail_label);

    tmp = tcg_temp_new_i64();
    if (is_pair) {
        if (size == 2) {
            TCGv_i64 val = tcg_temp_new_i64();
            tcg_gen_concat32_i64(tmp, cpu_reg(s, rt), cpu_reg(s, rt2));
            tcg_gen_concat32_i64(val, cpu_exclusive_val, cpu_exclusive_high);
            tcg_gen_atomic_cmpxchg_i64(tmp, addr, val, tmp,
                                       get_mem_index(s),
                                       size | MO_ALIGN | s->be_data);
            tcg_gen_setcond_i64(TCG_COND_NE, tmp, tmp, val);
            tcg_temp_free_i64(val);
        } else if (s->be_data == MO_LE) {
            gen_helper_paired_cmpxchg64_le(tmp, cpu_env, addr, cpu_reg(s, rt),
                                           cpu_reg(s, rt2));
        } else {
            gen_helper_paired_cmpxchg64_be(tmp, cpu_env, addr, cpu_reg(s, rt),
                                           cpu_reg(s, rt2));
        }

        /* Xilinx: We need a few changes in here to ensure that our
         * randomised testing software works with exclusive stores.
         */
        TCGv_i64 addrhi = tcg_temp_new_i64();

        tcg_gen_addi_i64(addrhi, addr, 1 << size);
        tcg_gen_qemu_st_i64(cpu_reg(s, rt2), addrhi,
                            get_mem_index(s), s->be_data + size);
        tcg_temp_free_i64(addrhi);
    } else {
        tcg_gen_qemu_st_i64(cpu_reg(s, rt), addr, get_mem_index(s),
                            s->be_data + size);
    }

    tcg_temp_free_i64(addr);

    tcg_gen_movi_i64(cpu_reg(s, rd), 0);
    tcg_temp_free_i64(tmp);
    tcg_gen_br(done_label);

    gen_set_label(fail_label);
    tcg_gen_movi_i64(cpu_reg(s, rd), 1);
    gen_set_label(done_label);
    tcg_gen_movi_i64(cpu_exclusive_addr, -1);

    gen_helper_sev(cpu_env);
}

/* Update the Sixty-Four bit (SF) registersize. This logic is derived
 * from the ARMv8 specs for LDR (Shared decode for all encodings).
 */
static bool disas_ldst_compute_iss_sf(int size, bool is_signed, int opc)
{
    int opc0 = extract32(opc, 0, 1);
    int regsize;

    if (is_signed) {
        regsize = opc0 ? 32 : 64;
    } else {
        regsize = size == 3 ? 64 : 32;
    }
    return regsize == 64;
}

/* C3.3.6 Load/store exclusive
 *
 *  31 30 29         24  23  22   21  20  16  15  14   10 9    5 4    0
 * +-----+-------------+----+---+----+------+----+-------+------+------+
 * | sz  | 0 0 1 0 0 0 | o2 | L | o1 |  Rs  | o0 |  Rt2  |  Rn  | Rt   |
 * +-----+-------------+----+---+----+------+----+-------+------+------+
 *
 *  sz: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64 bit
 *   L: 0 -> store, 1 -> load
 *  o2: 0 -> exclusive, 1 -> not
 *  o1: 0 -> single register, 1 -> register pair
 *  o0: 1 -> load-acquire/store-release, 0 -> not
 */
static void disas_ldst_excl(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int rt2 = extract32(insn, 10, 5);
    int is_lasr = extract32(insn, 15, 1);
    int rs = extract32(insn, 16, 5);
    int is_pair = extract32(insn, 21, 1);
    int is_store = !extract32(insn, 22, 1);
    int is_excl = !extract32(insn, 23, 1);
    int size = extract32(insn, 30, 2);
    TCGv_i64 tcg_addr;

    if ((!is_excl && !is_pair && !is_lasr) ||
        (!is_excl && is_pair) ||
        (is_pair && size < 2)) {
        unallocated_encoding(s);
        return;
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    /* Note that since TCG is single threaded load-acquire/store-release
     * semantics require no extra if (is_lasr) { ... } handling.
     */

    if (is_excl) {
        if (!is_store) {
            s->is_ldex = true;
            gen_load_exclusive(s, rt, rt2, tcg_addr, size, is_pair);
            if (is_lasr) {
                tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
            }
        } else {
            if (is_lasr) {
                tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
            }
            gen_store_exclusive(s, rs, rt, rt2, tcg_addr, size, is_pair);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        bool iss_sf = disas_ldst_compute_iss_sf(size, false, 0);

        /* Generate ISS for non-exclusive accesses including LASR.  */
        if (is_store) {
            if (is_lasr) {
                tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
            }
            do_gpr_st(s, tcg_rt, tcg_addr, size,
                      true, rt, iss_sf, is_lasr);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, false, false,
                      true, rt, iss_sf, is_lasr);
            if (is_lasr) {
                tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
            }
        }
    }
}

/*
 * C3.3.5 Load register (literal)
 *
 *  31 30 29   27  26 25 24 23                5 4     0
 * +-----+-------+---+-----+-------------------+-------+
 * | opc | 0 1 1 | V | 0 0 |     imm19         |  Rt   |
 * +-----+-------+---+-----+-------------------+-------+
 *
 * V: 1 -> vector (simd/fp)
 * opc (non-vector): 00 -> 32 bit, 01 -> 64 bit,
 *                   10-> 32 bit signed, 11 -> prefetch
 * opc (vector): 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit (11 unallocated)
 */
static void disas_ld_lit(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int64_t imm = sextract32(insn, 5, 19) << 2;
    bool is_vector = extract32(insn, 26, 1);
    int opc = extract32(insn, 30, 2);
    bool is_signed = false;
    int size = 2;
    TCGv_i64 tcg_rt, tcg_addr;

    if (is_vector) {
        if (opc == 3) {
            unallocated_encoding(s);
            return;
        }
        size = 2 + opc;
        if (!fp_access_check(s)) {
            return;
        }
    } else {
        if (opc == 3) {
            /* PRFM (literal) : prefetch */
            return;
        }
        size = 2 + extract32(opc, 0, 1);
        is_signed = extract32(opc, 1, 1);
    }

    tcg_rt = cpu_reg(s, rt);

    tcg_addr = tcg_const_i64((s->pc - 4) + imm);
    if (is_vector) {
        do_fp_ld(s, rt, tcg_addr, size);
    } else {
        /* Only unsigned 32bit loads target 32bit registers.  */
        bool iss_sf = opc != 0;

        do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, false,
                  true, rt, iss_sf, false);
    }
    tcg_temp_free_i64(tcg_addr);
}

/*
 * C5.6.80 LDNP (Load Pair - non-temporal hint)
 * C5.6.81 LDP (Load Pair - non vector)
 * C5.6.82 LDPSW (Load Pair Signed Word - non vector)
 * C5.6.176 STNP (Store Pair - non-temporal hint)
 * C5.6.177 STP (Store Pair - non vector)
 * C6.3.165 LDNP (Load Pair of SIMD&FP - non-temporal hint)
 * C6.3.165 LDP (Load Pair of SIMD&FP)
 * C6.3.284 STNP (Store Pair of SIMD&FP - non-temporal hint)
 * C6.3.284 STP (Store Pair of SIMD&FP)
 *
 *  31 30 29   27  26  25 24   23  22 21   15 14   10 9    5 4    0
 * +-----+-------+---+---+-------+---+-----------------------------+
 * | opc | 1 0 1 | V | 0 | index | L |  imm7 |  Rt2  |  Rn  | Rt   |
 * +-----+-------+---+---+-------+---+-------+-------+------+------+
 *
 * opc: LDP/STP/LDNP/STNP        00 -> 32 bit, 10 -> 64 bit
 *      LDPSW                    01
 *      LDP/STP/LDNP/STNP (SIMD) 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit
 *   V: 0 -> GPR, 1 -> Vector
 * idx: 00 -> signed offset with non-temporal hint, 01 -> post-index,
 *      10 -> signed offset, 11 -> pre-index
 *   L: 0 -> Store 1 -> Load
 *
 * Rt, Rt2 = GPR or SIMD registers to be stored
 * Rn = general purpose register containing address
 * imm7 = signed offset (multiple of 4 or 8 depending on size)
 */
static void disas_ldst_pair(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int rt2 = extract32(insn, 10, 5);
    uint64_t offset = sextract64(insn, 15, 7);
    int index = extract32(insn, 23, 2);
    bool is_vector = extract32(insn, 26, 1);
    bool is_load = extract32(insn, 22, 1);
    int opc = extract32(insn, 30, 2);

    bool is_signed = false;
    bool postindex = false;
    bool wback = false;

    TCGv_i64 tcg_addr; /* calculated address */
    int size;

    if (opc == 3) {
        unallocated_encoding(s);
        return;
    }

    if (is_vector) {
        size = 2 + opc;
    } else {
        size = 2 + extract32(opc, 1, 1);
        is_signed = extract32(opc, 0, 1);
        if (!is_load && is_signed) {
            unallocated_encoding(s);
            return;
        }
    }

    switch (index) {
    case 1: /* post-index */
        postindex = true;
        wback = true;
        break;
    case 0:
        /* signed offset with "non-temporal" hint. Since we don't emulate
         * caches we don't care about hints to the cache system about
         * data access patterns, and handle this identically to plain
         * signed offset.
         */
        if (is_signed) {
            /* There is no non-temporal-hint version of LDPSW */
            unallocated_encoding(s);
            return;
        }
        postindex = false;
        break;
    case 2: /* signed offset, rn not updated */
        postindex = false;
        break;
    case 3: /* pre-index */
        postindex = false;
        wback = true;
        break;
    }

    if (is_vector && !fp_access_check(s)) {
        return;
    }

    offset <<= size;

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }

    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    if (!postindex) {
        tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);
    }

    if (is_vector) {
        if (is_load) {
            do_fp_ld(s, rt, tcg_addr, size);
        } else {
            do_fp_st(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        if (is_load) {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, false,
                      false, 0, false, false);
        } else {
            do_gpr_st(s, tcg_rt, tcg_addr, size,
                      false, 0, false, false);
        }
    }
    tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size);
    if (is_vector) {
        if (is_load) {
            do_fp_ld(s, rt2, tcg_addr, size);
        } else {
            do_fp_st(s, rt2, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt2 = cpu_reg(s, rt2);
        if (is_load) {
            do_gpr_ld(s, tcg_rt2, tcg_addr, size, is_signed, false,
                      false, 0, false, false);
        } else {
            do_gpr_st(s, tcg_rt2, tcg_addr, size,
                      false, 0, false, false);
        }
    }

    if (wback) {
        if (postindex) {
            tcg_gen_addi_i64(tcg_addr, tcg_addr, offset - (1 << size));
        } else {
            tcg_gen_subi_i64(tcg_addr, tcg_addr, 1 << size);
        }
        tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr);
    }
}

/*
 * C3.3.8 Load/store (immediate post-indexed)
 * C3.3.9 Load/store (immediate pre-indexed)
 * C3.3.12 Load/store (unscaled immediate)
 *
 * 31 30 29   27  26 25 24 23 22 21  20    12 11 10 9    5 4    0
 * +----+-------+---+-----+-----+---+--------+-----+------+------+
 * |size| 1 1 1 | V | 0 0 | opc | 0 |  imm9  | idx |  Rn  |  Rt  |
 * +----+-------+---+-----+-----+---+--------+-----+------+------+
 *
 * idx = 01 -> post-indexed, 11 pre-indexed, 00 unscaled imm. (no writeback)
         10 -> unprivileged
 * V = 0 -> non-vector
 * size: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64bit
 * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
 */
static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn,
                                int opc,
                                int size,
                                int rt,
                                bool is_vector)
{
    int rn = extract32(insn, 5, 5);
    int imm9 = sextract32(insn, 12, 9);
    int idx = extract32(insn, 10, 2);
    bool is_signed = false;
    bool is_store = false;
    bool is_extended = false;
    bool is_unpriv = (idx == 2);
    bool iss_valid = !is_vector;
    bool post_index;
    bool writeback;

    TCGv_i64 tcg_addr;

    if (is_vector) {
        size |= (opc & 2) << 1;
        if (size > 4 || is_unpriv) {
            unallocated_encoding(s);
            return;
        }
        is_store = ((opc & 1) == 0);
        if (!fp_access_check(s)) {
            return;
        }
    } else {
        if (size == 3 && opc == 2) {
            /* PRFM - prefetch */
            if (is_unpriv) {
                unallocated_encoding(s);
                return;
            }
            return;
        }
        if (opc == 3 && size > 1) {
            unallocated_encoding(s);
            return;
        }
        is_store = (opc == 0);
        is_signed = extract32(opc, 1, 1);
        is_extended = (size < 3) && extract32(opc, 0, 1);
    }

    switch (idx) {
    case 0:
    case 2:
        post_index = false;
        writeback = false;
        break;
    case 1:
        post_index = true;
        writeback = true;
        break;
    case 3:
        post_index = false;
        writeback = true;
        break;
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    if (!post_index) {
        tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9);
    }

    if (is_vector) {
        if (is_store) {
            do_fp_st(s, rt, tcg_addr, size);
        } else {
            do_fp_ld(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        int memidx = is_unpriv ? get_a64_user_mem_index(s) : get_mem_index(s);
        bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc);

        if (is_store) {
            do_gpr_st_memidx(s, tcg_rt, tcg_addr, size, memidx,
                             iss_valid, rt, iss_sf, false);
        } else {
            do_gpr_ld_memidx(s, tcg_rt, tcg_addr, size,
                             is_signed, is_extended, memidx,
                             iss_valid, rt, iss_sf, false);
        }
    }

    if (writeback) {
        TCGv_i64 tcg_rn = cpu_reg_sp(s, rn);
        if (post_index) {
            tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9);
        }
        tcg_gen_mov_i64(tcg_rn, tcg_addr);
    }
}

/*
 * C3.3.10 Load/store (register offset)
 *
 * 31 30 29   27  26 25 24 23 22 21  20  16 15 13 12 11 10 9  5 4  0
 * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+
 * |size| 1 1 1 | V | 0 0 | opc | 1 |  Rm  | opt | S| 1 0 | Rn | Rt |
 * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+
 *
 * For non-vector:
 *   size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit
 *   opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
 * For vector:
 *   size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated
 *   opc<0>: 0 -> store, 1 -> load
 * V: 1 -> vector/simd
 * opt: extend encoding (see DecodeRegExtend)
 * S: if S=1 then scale (essentially index by sizeof(size))
 * Rt: register to transfer into/out of
 * Rn: address register or SP for base
 * Rm: offset register or ZR for offset
 */
static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn,
                                   int opc,
                                   int size,
                                   int rt,
                                   bool is_vector)
{
    int rn = extract32(insn, 5, 5);
    int shift = extract32(insn, 12, 1);
    int rm = extract32(insn, 16, 5);
    int opt = extract32(insn, 13, 3);
    bool is_signed = false;
    bool is_store = false;
    bool is_extended = false;

    TCGv_i64 tcg_rm;
    TCGv_i64 tcg_addr;

    if (extract32(opt, 1, 1) == 0) {
        unallocated_encoding(s);
        return;
    }

    if (is_vector) {
        size |= (opc & 2) << 1;
        if (size > 4) {
            unallocated_encoding(s);
            return;
        }
        is_store = !extract32(opc, 0, 1);
        if (!fp_access_check(s)) {
            return;
        }
    } else {
        if (size == 3 && opc == 2) {
            /* PRFM - prefetch */
            return;
        }
        if (opc == 3 && size > 1) {
            unallocated_encoding(s);
            return;
        }
        is_store = (opc == 0);
        is_signed = extract32(opc, 1, 1);
        is_extended = (size < 3) && extract32(opc, 0, 1);
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    tcg_rm = read_cpu_reg(s, rm, 1);
    ext_and_shift_reg(tcg_rm, tcg_rm, opt, shift ? size : 0);

    tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_rm);

    if (is_vector) {
        if (is_store) {
            do_fp_st(s, rt, tcg_addr, size);
        } else {
            do_fp_ld(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc);
        if (is_store) {
            do_gpr_st(s, tcg_rt, tcg_addr, size,
                      true, rt, iss_sf, false);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size,
                      is_signed, is_extended,
                      true, rt, iss_sf, false);
        }
    }
}

/*
 * C3.3.13 Load/store (unsigned immediate)
 *
 * 31 30 29   27  26 25 24 23 22 21        10 9     5
 * +----+-------+---+-----+-----+------------+-------+------+
 * |size| 1 1 1 | V | 0 1 | opc |   imm12    |  Rn   |  Rt  |
 * +----+-------+---+-----+-----+------------+-------+------+
 *
 * For non-vector:
 *   size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit
 *   opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
 * For vector:
 *   size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated
 *   opc<0>: 0 -> store, 1 -> load
 * Rn: base address register (inc SP)
 * Rt: target register
 */
static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn,
                                        int opc,
                                        int size,
                                        int rt,
                                        bool is_vector)
{
    int rn = extract32(insn, 5, 5);
    unsigned int imm12 = extract32(insn, 10, 12);
    unsigned int offset;

    TCGv_i64 tcg_addr;

    bool is_store;
    bool is_signed = false;
    bool is_extended = false;

    if (is_vector) {
        size |= (opc & 2) << 1;
        if (size > 4) {
            unallocated_encoding(s);
            return;
        }
        is_store = !extract32(opc, 0, 1);
        if (!fp_access_check(s)) {
            return;
        }
    } else {
        if (size == 3 && opc == 2) {
            /* PRFM - prefetch */
            return;
        }
        if (opc == 3 && size > 1) {
            unallocated_encoding(s);
            return;
        }
        is_store = (opc == 0);
        is_signed = extract32(opc, 1, 1);
        is_extended = (size < 3) && extract32(opc, 0, 1);
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);
    offset = imm12 << size;
    tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);

    if (is_vector) {
        if (is_store) {
            do_fp_st(s, rt, tcg_addr, size);
        } else {
            do_fp_ld(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc);
        if (is_store) {
            do_gpr_st(s, tcg_rt, tcg_addr, size,
                      true, rt, iss_sf, false);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended,
                      true, rt, iss_sf, false);
        }
    }
}

/* Load/store register (all forms) */
static void disas_ldst_reg(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int opc = extract32(insn, 22, 2);
    bool is_vector = extract32(insn, 26, 1);
    int size = extract32(insn, 30, 2);

    switch (extract32(insn, 24, 2)) {
    case 0:
        if (extract32(insn, 21, 1) == 1 && extract32(insn, 10, 2) == 2) {
            disas_ldst_reg_roffset(s, insn, opc, size, rt, is_vector);
        } else {
            /* Load/store register (unscaled immediate)
             * Load/store immediate pre/post-indexed
             * Load/store register unprivileged
             */
            disas_ldst_reg_imm9(s, insn, opc, size, rt, is_vector);
        }
        break;
    case 1:
        disas_ldst_reg_unsigned_imm(s, insn, opc, size, rt, is_vector);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

/* C3.3.1 AdvSIMD load/store multiple structures
 *
 *  31  30  29           23 22  21         16 15    12 11  10 9    5 4    0
 * +---+---+---------------+---+-------------+--------+------+------+------+
 * | 0 | Q | 0 0 1 1 0 0 0 | L | 0 0 0 0 0 0 | opcode | size |  Rn  |  Rt  |
 * +---+---+---------------+---+-------------+--------+------+------+------+
 *
 * C3.3.2 AdvSIMD load/store multiple structures (post-indexed)
 *
 *  31  30  29           23 22  21  20     16 15    12 11  10 9    5 4    0
 * +---+---+---------------+---+---+---------+--------+------+------+------+
 * | 0 | Q | 0 0 1 1 0 0 1 | L | 0 |   Rm    | opcode | size |  Rn  |  Rt  |
 * +---+---+---------------+---+---+---------+--------+------+------+------+
 *
 * Rt: first (or only) SIMD&FP register to be transferred
 * Rn: base address or SP
 * Rm (post-index only): post-index register (when !31) or size dependent #imm
 */
static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int size = extract32(insn, 10, 2);
    int opcode = extract32(insn, 12, 4);
    bool is_store = !extract32(insn, 22, 1);
    bool is_postidx = extract32(insn, 23, 1);
    bool is_q = extract32(insn, 30, 1);
    TCGv_i64 tcg_addr, tcg_rn;

    int ebytes = 1 << size;
    int elements = (is_q ? 128 : 64) / (8 << size);
    int rpt;    /* num iterations */
    int selem;  /* structure elements */
    int r;

    if (extract32(insn, 31, 1) || extract32(insn, 21, 1)) {
        unallocated_encoding(s);
        return;
    }

    /* From the shared decode logic */
    switch (opcode) {
    case 0x0:
        rpt = 1;
        selem = 4;
        break;
    case 0x2:
        rpt = 4;
        selem = 1;
        break;
    case 0x4:
        rpt = 1;
        selem = 3;
        break;
    case 0x6:
        rpt = 3;
        selem = 1;
        break;
    case 0x7:
        rpt = 1;
        selem = 1;
        break;
    case 0x8:
        rpt = 1;
        selem = 2;
        break;
    case 0xa:
        rpt = 2;
        selem = 1;
        break;
    default:
        unallocated_encoding(s);
        return;
    }

    if (size == 3 && !is_q && selem != 1) {
        /* reserved */
        unallocated_encoding(s);
        return;
    }

    if (!fp_access_check(s)) {
        return;
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }

    tcg_rn = cpu_reg_sp(s, rn);
    tcg_addr = tcg_temp_new_i64();
    tcg_gen_mov_i64(tcg_addr, tcg_rn);

    for (r = 0; r < rpt; r++) {
        int e;
        for (e = 0; e < elements; e++) {
            int tt = (rt + r) % 32;
            int xs;
            for (xs = 0; xs < selem; xs++) {
                if (is_store) {
                    do_vec_st(s, tt, e, tcg_addr, size);
                } else {
                    do_vec_ld(s, tt, e, tcg_addr, size);

                    /* For non-quad operations, setting a slice of the low
                     * 64 bits of the register clears the high 64 bits (in
                     * the ARM ARM pseudocode this is implicit in the fact
                     * that 'rval' is a 64 bit wide variable). We optimize
                     * by noticing that we only need to do this the first
                     * time we touch a register.
                     */
                    if (!is_q && e == 0 && (r == 0 || xs == selem - 1)) {
                        clear_vec_high(s, tt);
                    }
                }
                tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
                tt = (tt + 1) % 32;
            }
        }
    }

    if (is_postidx) {
        int rm = extract32(insn, 16, 5);
        if (rm == 31) {
            tcg_gen_mov_i64(tcg_rn, tcg_addr);
        } else {
            tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
        }
    }
    tcg_temp_free_i64(tcg_addr);
}

/* C3.3.3 AdvSIMD load/store single structure
 *
 *  31  30  29           23 22 21 20       16 15 13 12  11  10 9    5 4    0
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 * | 0 | Q | 0 0 1 1 0 1 0 | L R | 0 0 0 0 0 | opc | S | size |  Rn  |  Rt  |
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 *
 * C3.3.4 AdvSIMD load/store single structure (post-indexed)
 *
 *  31  30  29           23 22 21 20       16 15 13 12  11  10 9    5 4    0
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 * | 0 | Q | 0 0 1 1 0 1 1 | L R |     Rm    | opc | S | size |  Rn  |  Rt  |
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 *
 * Rt: first (or only) SIMD&FP register to be transferred
 * Rn: base address or SP
 * Rm (post-index only): post-index register (when !31) or size dependent #imm
 * index = encoded in Q:S:size dependent on size
 *
 * lane_size = encoded in R, opc
 * transfer width = encoded in opc, S, size
 */
static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int size = extract32(insn, 10, 2);
    int S = extract32(insn, 12, 1);
    int opc = extract32(insn, 13, 3);
    int R = extract32(insn, 21, 1);
    int is_load = extract32(insn, 22, 1);
    int is_postidx = extract32(insn, 23, 1);
    int is_q = extract32(insn, 30, 1);

    int scale = extract32(opc, 1, 2);
    int selem = (extract32(opc, 0, 1) << 1 | R) + 1;
    bool replicate = false;
    int index = is_q << 3 | S << 2 | size;
    int ebytes, xs;
    TCGv_i64 tcg_addr, tcg_rn;

    switch (scale) {
    case 3:
        if (!is_load || S) {
            unallocated_encoding(s);
            return;
        }
        scale = size;
        replicate = true;
        break;
    case 0:
        break;
    case 1:
        if (extract32(size, 0, 1)) {
            unallocated_encoding(s);
            return;
        }
        index >>= 1;
        break;
    case 2:
        if (extract32(size, 1, 1)) {
            unallocated_encoding(s);
            return;
        }
        if (!extract32(size, 0, 1)) {
            index >>= 2;
        } else {
            if (S) {
                unallocated_encoding(s);
                return;
            }
            index >>= 3;
            scale = 3;
        }
        break;
    default:
        g_assert_not_reached();
    }

    if (!fp_access_check(s)) {
        return;
    }

    ebytes = 1 << scale;

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }

    tcg_rn = cpu_reg_sp(s, rn);
    tcg_addr = tcg_temp_new_i64();
    tcg_gen_mov_i64(tcg_addr, tcg_rn);

    for (xs = 0; xs < selem; xs++) {
        if (replicate) {
            /* Load and replicate to all elements */
            uint64_t mulconst;
            TCGv_i64 tcg_tmp = tcg_temp_new_i64();

            tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr,
                                get_mem_index(s), s->be_data + scale);
            switch (scale) {
            case 0:
                mulconst = 0x0101010101010101ULL;
                break;
            case 1:
                mulconst = 0x0001000100010001ULL;
                break;
            case 2:
                mulconst = 0x0000000100000001ULL;
                break;
            case 3:
                mulconst = 0;
                break;
            default:
                g_assert_not_reached();
            }
            if (mulconst) {
                tcg_gen_muli_i64(tcg_tmp, tcg_tmp, mulconst);
            }
            write_vec_element(s, tcg_tmp, rt, 0, MO_64);
            if (is_q) {
                write_vec_element(s, tcg_tmp, rt, 1, MO_64);
            } else {
                clear_vec_high(s, rt);
            }
            tcg_temp_free_i64(tcg_tmp);
        } else {
            /* Load/store one element per register */
            if (is_load) {
                do_vec_ld(s, rt, index, tcg_addr, scale);
            } else {
                do_vec_st(s, rt, index, tcg_addr, scale);
            }
        }
        tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
        rt = (rt + 1) % 32;
    }

    if (is_postidx) {
        int rm = extract32(insn, 16, 5);
        if (rm == 31) {
            tcg_gen_mov_i64(tcg_rn, tcg_addr);
        } else {
            tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
        }
    }
    tcg_temp_free_i64(tcg_addr);
}

/* C3.3 Loads and stores */
static void disas_ldst(DisasContext *s, uint32_t insn)
{
    switch (extract32(insn, 24, 6)) {
    case 0x08: /* Load/store exclusive */
        disas_ldst_excl(s, insn);
        break;
    case 0x18: case 0x1c: /* Load register (literal) */
        disas_ld_lit(s, insn);
        break;
    case 0x28: case 0x29:
    case 0x2c: case 0x2d: /* Load/store pair (all forms) */
        disas_ldst_pair(s, insn);
        break;
    case 0x38: case 0x39:
    case 0x3c: case 0x3d: /* Load/store register (all forms) */
        disas_ldst_reg(s, insn);
        break;
    case 0x0c: /* AdvSIMD load/store multiple structures */
        disas_ldst_multiple_struct(s, insn);
        break;
    case 0x0d: /* AdvSIMD load/store single structure */
        disas_ldst_single_struct(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

/* C3.4.6 PC-rel. addressing
 *   31  30   29 28       24 23                5 4    0
 * +----+-------+-----------+-------------------+------+
 * | op | immlo | 1 0 0 0 0 |       immhi       |  Rd  |
 * +----+-------+-----------+-------------------+------+
 */
static void disas_pc_rel_adr(DisasContext *s, uint32_t insn)
{
    unsigned int page, rd;
    uint64_t base;
    uint64_t offset;

    page = extract32(insn, 31, 1);
    /* SignExtend(immhi:immlo) -> offset */
    offset = sextract64(insn, 5, 19);
    offset = offset << 2 | extract32(insn, 29, 2);
    rd = extract32(insn, 0, 5);
    base = s->pc - 4;

    if (page) {
        /* ADRP (page based) */
        base &= ~0xfff;
        offset <<= 12;
    }

    tcg_gen_movi_i64(cpu_reg(s, rd), base + offset);
}

/*
 * C3.4.1 Add/subtract (immediate)
 *
 *  31 30 29 28       24 23 22 21         10 9   5 4   0
 * +--+--+--+-----------+-----+-------------+-----+-----+
 * |sf|op| S| 1 0 0 0 1 |shift|    imm12    |  Rn | Rd  |
 * +--+--+--+-----------+-----+-------------+-----+-----+
 *
 *    sf: 0 -> 32bit, 1 -> 64bit
 *    op: 0 -> add  , 1 -> sub
 *     S: 1 -> set flags
 * shift: 00 -> LSL imm by 0, 01 -> LSL imm by 12
 */
static void disas_add_sub_imm(DisasContext *s, uint32_t insn)
{
    int rd = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    uint64_t imm = extract32(insn, 10, 12);
    int shift = extract32(insn, 22, 2);
    bool setflags = extract32(insn, 29, 1);
    bool sub_op = extract32(insn, 30, 1);
    bool is_64bit = extract32(insn, 31, 1);

    TCGv_i64 tcg_rn = cpu_reg_sp(s, rn);
    TCGv_i64 tcg_rd = setflags ? cpu_reg(s, rd) : cpu_reg_sp(s, rd);
    TCGv_i64 tcg_result;

    switch (shift) {
    case 0x0:
        break;
    case 0x1:
        imm <<= 12;
        break;
    default:
        unallocated_encoding(s);
        return;
    }

    tcg_result = tcg_temp_new_i64();
    if (!setflags) {
        if (sub_op) {
            tcg_gen_subi_i64(tcg_result, tcg_rn, imm);
        } else {
            tcg_gen_addi_i64(tcg_result, tcg_rn, imm);
        }
    } else {
        TCGv_i64 tcg_imm = tcg_const_i64(imm);
        if (sub_op) {
            gen_sub_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
        } else {
            gen_add_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
        }
        tcg_temp_free_i64(tcg_imm);
    }

    if (is_64bit) {
        tcg_gen_mov_i64(tcg_rd, tcg_result);
    } else {
        tcg_gen_ext32u_i64(tcg_rd, tcg_result);
    }

    tcg_temp_free_i64(tcg_result);
}

/* The input should be a value in the bottom e bits (with higher
 * bits zero); returns that value replicated into every element
 * of size e in a 64 bit integer.
 */
static uint64_t bitfield_replicate(uint64_t mask, unsigned int e)
{
    assert(e != 0);
    while (e < 64) {
        mask |= mask << e;
        e *= 2;
    }
    return mask;
}